Decision Sufficiency of Learned Representation Interfaces for Safe Generative Control

Abstract

A controller can guide a language model toward safe and useful responses by choosing when to assist, ask for clarification, or refuse. When the controller uses selected internal features, poor performance alone cannot distinguish missing information from limitations of its decision rules or training. We study decision sufficiency: whether the best controller using a representation can match the minimum average loss attainable with full state information, under the same strategies and evaluation criteria. For interfaces with finitely many outputs, we compute the optimal loss exactly and separate the three sources of excess loss. Pairwise checks can miss information loss: states with the same controller input may share an optimal strategy in every pair but not across the whole group. We bound the number of states needed to reveal a conflict and characterize the fewest outputs an unrestricted interface needs to avoid all conflicts. We audit selected features from sparse autoencoders, which encode model activations using relatively few active features, in Qwen2.5, SmolLM2, and Phi. On SmolLM2 responses scored by two human raters, restricting the controller to two selected on/off features increases its minimum average loss by 0.0345--0.1166 relative to full state information, even with the governing policy supplied. Both independently trained autoencoders show the increase on both evaluation sets. The audit identifies decision failures that require changing the controller's input, not merely its architecture or training.